NotesFAQContact Us
Collection
Advanced
Search Tips
Back to results
ERIC Number: ED645752
Record Type: Non-Journal
Publication Date: 2023
Pages: 130
Abstractor: As Provided
ISBN: 979-8-3816-9736-0
ISSN: N/A
EISSN: N/A
Available Date: N/A
Investigating User Trust in Context-Aware Recommender Systems in Search as Learning
Neha Rani
ProQuest LLC, Ph.D. Dissertation, University of Florida
With the growth of digital media, learners are presented with multiple options to choose from when looking for resources to learn from. Learning that happens during searching for items to learn from is called Search-as-Learning (SaL). Recommender Systems (RS) can aid in SaL by reducing information overload and providing item suggestions. An emerging technique is to use users context (information about users current situation) with other filtering mechanisms to generate more relevant recommendations. Such RS are called Context-Aware Recommender Systems (CARS). Trust has been long found to contribute towards the acceptance of a system. Trust is users belief in the system and its intentions. The literature emphasizes the need to build trustworthy RS. RS are complicated automated systems whose functioning is not apparent to users, creating a lack of transparency and understanding, leading to the need to build a trustworthy RS. Further, instances of errors or irrelevant recommendations can lead to quick distrust. CARS may further add to the lack of trust due to the automatic context detection, third-party data sources to gather users context, and lack of user involvement. My dissertation research investigates how to build trust in CARS. This dissertation explores trust in CARS through three main steps: Understanding - investigating the need for trust towards CARS and users perception of CARS in an educational context; Exploring - exploring design elements that have the potential to impact users trust and acceptance of recommendations; Synthesizing - developing design guidelines for trustworthy CARS. I have conducted a total of four user studies. I explored users perceptions of CARS and the need for trust in CARS using a survey-based user study. Then, I present my initial investigation of how the presence of an explanation in CARS impacts users trust, perception, and preference. Explanations have been explored to support trust through building an understanding of the system. I explored the impact of user control and levels of user control as a design element on users trust and perception. I also investigated the role of user feedback in building trust towards CARS. Finally, I synthesize the findings and develop design guidelines for designing trustworthy CARS. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com.bibliotheek.ehb.be/en-US/products/dissertations/individuals.shtml.]
ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com.bibliotheek.ehb.be/en-US/products/dissertations/individuals.shtml
Publication Type: Dissertations/Theses - Doctoral Dissertations
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A
Author Affiliations: N/A